通过稀疏像素与稀疏基元加速3D高斯点渲染，提升速度并减小模型。
Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
- 精准定位高斯点，优化渲染流程以提升速度。
- 引入新剪枝方法，使模型更小、训练更快。
- 适用于资源受限场景，兼顾速度与画质。
3D高斯点渲染（3D-GS）是一种新兴的3D场景重建技术，通过可微分的3D高斯点云实现新视角的实时渲染。然而，在资源受限环境下，其渲染速度与模型规模仍存在瓶颈。本文识别并解决3D-GS中的两大效率问题：首先优化渲染管线，精确定位场景中的高斯点，显著提升渲染速度而不损失视觉质量；其次提出一种新型剪枝策略，并集成至训练流程中，大幅降低模型尺寸与训练时间，同时进一步加快渲染速度。所提出的Speedy-Splat方法在Mip-NeRF 360、Tanks & Temples和Deep Blending数据集上的平均渲染速度提升达6.71倍。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. However, its rendering speed and model size still present bottlenecks, especially in resource-constrained settings. In this paper, we identify and address two key inefficiencies in 3D-GS to substantially improve rendering speed. These improvements also yield the ancillary benefits of reduced model size and training time. First, we optimize the rendering pipeline to precisely localize Gaussians in the scene, boosting rendering speed without altering visual fidelity. Second, we introduce a novel pruning technique and integrate it into the training pipeline, significantly reducing model size and training time while further raising rendering speed. Our Speedy-Splat approach combines these techniques to accelerate average rendering speed by a drastic $\mathit{6.71\times}$ across scenes from the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。